© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 3180
    Prev
    Next
    INDEX
    Explanations

    acronyms known as 'IF' with various levels of emphasis by the activation values

    oai_token-act-pair · gpt-3.5-turbo

    instances of the acronym "IF" and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.70
    hra
    -0.69
    laus
    -0.66
    holm
    -0.63
     Conquest
    -0.61
    heimer
    -0.61
     alternating
    -0.60
     rotor
    -0.60
    clone
    -0.60
    Downloadha
    -0.59
    POSITIVE LOGITS
    IF
    1.13
    ICA
    1.03
    TY
    1.00
    FER
    0.96
    IL
    0.93
    IELD
    0.91
    IK
    0.88
    IB
    0.87
    FIN
    0.86
    ornia
    0.86
    Activations Density 0.007%

    No Known Activations